Research on the Brain Tumor Image Segmentation Algorithm Based on an Improved UNet++ Model

针对计算机辅助脑肿瘤图像边缘分割模糊、分割精度不高等问题，提出了一种改进的嵌套UNet++脑肿瘤图像分割算法。首先设计MCAM (Mish Coordinate Attention Module)模块代替原UNet++的特征提取部分，嵌入坐标注意力机制(Coordinate Attention, CA)关注不同方向上的位置信息以增强特征提取能力，使用Mish激活函数替换ReLU激活函数防止出现梯度消失，提高脑肿瘤图像分割精度和泛化能力；其次在特征提取后加入SME (Squeeze Mish Excitation Block)模块进行挤压和激励，扩大特征图的感受野以增强对肿瘤特征的学习能力；最后利用焦点Dice损失函数关注模糊样本的分割，从而改善脑肿瘤图像边缘分割模糊的问题。提出的算法在Figshare数据集上进行仿真实验，实验结果表明在MIoU、MPA、Dice和Hausdorff评估指标上分别达到83.26%、81.91%、86.45%和18.57 mm。与3DUnet、Swin-UNet、DD-UNet、LRAE-UNet和AI-UNet等主流算法进行对比，证明提出的算法分割效果更优。 Aiming at the problems of blurred edge segmentation and low segmentation accuracy of computer-aided brain tumor images, an improved nested UNet++ brain tumor image segmentation algorithm was proposed. Firstly, the MCAM module is designed to replace the feature extraction part of the original UNet++. The CA attention mechanism is used to focus on positioning information in different directions to improve feature extraction capabilities. The Mish activation function is used to replace the ReLU activation function to prevent gradient disappearance and improve segmentation. Accuracy and generalization ability; then add the SME module after feature extraction for squeezing and excitation to enhance the receptive field of the feature map to enhance the learning ability of tumor features; finally, use the focus Dice loss function to focus on fuzzy samples segmentation, thereby improving the problem of blurred edge segmentation of brain tumor images. The proposed algorithm was simulated on the Figshare dataset. The experimental results showed that it achieved 83.26%, 81.91%, 86.45% and 18.57 mm in MIoU, MPA, Dice and Hausdorff evaluation indicators respectively. Comparison with algorithms such as 3DUnet, Swin-UNet, DD-UNet, LRAE-UNet and AI-UNet proves that the proposed algorithm has a better segmentation effect.